Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    United Nations or States

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     foreach
    0.53
     detal
    0.53
    кает
    0.51
     pericard
    0.50
     tī
    0.50
    arel
    0.49
     coprime
    0.48
     digestibility
    0.48
    точные
    0.48
    द्य
    0.48
    POSITIVE LOGITS
     Nations
    0.90
     Kingdom
    0.89
     States
    0.84
    Kingdom
    0.78
    States
    0.71
     Königreich
    0.70
     STATES
    0.69
    王国
    0.64
     Kingdoms
    0.63
     фрон
    0.61
    Act Density 0.039%

    No Known Activations